• 대한전기학회논문지
• /
• 제43권4호
• /
• pp.687-690
• /
• 1994

This paper presents a method of obtaining transmission network equivalents from the network's response to the pulse excitation signal. Proposed method is base on Prony signal analysis and jtransfer function identification technique. As a result Thevenin-type of discrete-time filter model can be generated. It can reproduce the driving point impedance characteristic of the network.

• 대한전기학회논문지
• /
• 제41권1호
• /
• pp.1-8
• /
• 1992

Hopfield neural network has been applied to the problem of economic load dispatch(ELD) of electric power. The optimum values of neuron potentials are represented in terms of large numbers. The differential synchronous transition mode is used in this simulation. Through case studies, we have shown the possibility of the application of neural network to ELD. In case of including the transmission losses, the proposed method has an advantage that the problem can be solved simply with one neural network, without calculating incremental fuel costs and incremental losses required by traditional method.

• 대한전기학회논문지
• /
• 제45권3호
• /
• pp.444-450
• /
• 1996

A digital hardware architecture for artificial neural network with learning capability is described in this paper. It is a modified hardware architecture known as HANNIBAL(Hardware Architecture for Neural Networks Implementing Back propagation Algorithm Learning). For implementing an efficient neural network hardware, we analyzed various type of multiplier which is major function block of neuro-processor cell. With this result, we design a efficient digital neural network hardware using serial/parallel multiplier, and test the operation. We also analyze the hardware efficiency with logic level simulation. (author). refs., figs., tabs.

• 대한전기학회논문지
• /
• 제39권5호
• /
• pp.519-526
• /
• 1990

In this paper we propose the resolved motion controller using a neural network for a robot manipulator. Neural identifier designed by a neural network is trained by using a feedback force as an error signal. The identifier approximates the output of a unknown nonlinear system by monitoring both the input and the output of this system. If the neural network is sufficiently trained well, it does not require either strict modelling of the manipulator or precise parameter estimation. The effectiveness of the proposed controller is demonstrated by computer simulation using a two-link planar robot.

• 전기학회논문지
• /
• 제66권12호
• /
• pp.1772-1781
• /
• 2017

In this study, the design methodology for alleviating the overfitting problem of Polynomial Neural Networks(PNN) is realized with the aid of two kinds techniques such as L2 regularization and Sum of Squared Coefficients (SSC). The PNN is widely used as a kind of mathematical modeling methods such as the identification of linear system by input/output data and the regression analysis modeling method for prediction problem. PNN is an algorithm that obtains preferred network structure by generating consecutive layers as well as nodes by using a multivariate polynomial subexpression. It has much fewer nodes and more flexible adaptability than existing neural network algorithms. However, such algorithms lead to overfitting problems due to noise sensitivity as well as excessive trainning while generation of successive network layers. To alleviate such overfitting problem and also effectively design its ensuing deep network structure, two techniques are introduced. That is we use the two techniques of both SSC(Sum of Squared Coefficients) and $L_2$ regularization for consecutive generation of each layer's nodes as well as each layer in order to construct the deep PNN structure. The technique of $L_2$ regularization is used for the minimum coefficient estimation by adding penalty term to cost function. $L_2$ regularization is a kind of representative methods of reducing the influence of noise by flattening the solution space and also lessening coefficient size. The technique for the SSC is implemented for the minimization of Sum of Squared Coefficients of polynomial instead of using the square of errors. In the sequel, the overfitting problem of the deep PNN structure is stabilized by the proposed method. This study leads to the possibility of deep network structure design as well as big data processing and also the superiority of the network performance through experiments is shown.

• 대한전기학회논문지
• /
• 제39권12호
• /
• pp.1306-1316
• /
• 1990

A controller using a multilayer neural network is proposed to the dynamic control of a PUMA 560 robot arm. This controller is developed based on an error back-propagation (BP) neural network. Since the neural network can model an arbitrary nonlinear mapping, it is used as a commanded feedforward torque generator. A Proportional Derivative (PD) feedback controller is used in parallel with the feedforward neural network to train the system. The neural network was trained by the current state of the manipulator as well as the PD feedback error torque. No a priori knowledge on system dynamics is needed and this information is rather implicitly stored in the interconnection weights of the neural network. In another experiment, the neural network was trained with the current, past and future positions only without any use of velocity sensors. Form this thim window of position values, BP network implicitly filters out the velocity and acceleration components for each joint. Computer simulation demonstrates such powerful characteristics of the neurocontroller as adaptation to changing environments, robustness to sensor noise, and continuous performance improvement with self-learning.

• 전기학회논문지
• /
• 제57권11호
• /
• pp.2095-2101
• /
• 2008

In this paper, we consider a performance improvement of neural network for predicting defect size of steam generator tube using early stopping. Usually, neural network is trained until MSE becomes less than a prescribed error goal. The smaller the error goal, the greater the prediction performance for the trained data. However, as the error goal is decreased, an over fitting is likely to start during supervised training of a neural network, which usually deteriorates the generalization performance. We propose that, for the prediction of an axisymmetric defect size, early stopping can be used to avoid the over-fitting. Through various experiments on the axisymmetric defect samples, we found that the difference bet ween the prediction error of neural network based on early stopping and that of ideal neural network is reasonably small. This indicates that the error goal used for neural network training for the prediction of defect size can be efficiently selected by early stopping.

• 대한전기학회논문지
• /
• 제41권4호
• /
• pp.400-410
• /
• 1992

This paper deals with a design of neural network control architectures for robot motion. Three types of control architectures are designed as follows : 1) a neural network control architecture which has the same characteristics as computed torque method 2) a neural network control architecture for compensating the control error on computed torque method with fixed feedback gain 3) neural network adaptive control architecture. Computer simulation of PUMA manipulator with 6 links is conducted for robot motion in order to examine the proposed neural network control architectures.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권12호
• /
• pp.804-810
• /
• 2004

There are two important things for the general purpose neural network processor. The first is a capability to build various structures of neural network, and the second is to be able to support suitable learning method for that neural network. Some way to process various learning algorithms is required for on-chip learning, because the more neural network types are to be handled, the more learning methods need to be built into. In this paper, an improved hardware structure is proposed to compute various kinds of learning algorithms flexibly. The hardware structure is based on the existing modular neural network structure. It doesn't need to add a new circuit or a new program for the learning process. It is shown that rearrangements of the existing processing elements can produce several neural network learning modules. The performance and utilization of this module are analyzed by comparing with other neural network chips.

• 조명전기설비학회논문지
• /
• 제24권10호
• /
• pp.49-57
• /
• 2010

In order to provide electricity to users economically and safely, distribution automation systems (DASs) monitor and operate components of distribution systems remotely through communication networks. The fiber optic communication network has been mainly installed for the DAS of Korea Electric Power Corporation (KEPCO) because of its huge bandwidth and dielectric noise immunity. However, the fiber optic communication network has some shortcomings that its installation cost and communication fee are expensive. This paper proposes a complex network where WLANs are combined with conventional fiber optic communication networks in order to expand DAS easily and inexpensively. A fixed wireless bridge communication unit (FWB-CU) for the proposed complex network is implemented using IEEE 802.11a WLAN technology. The proposed complex network is built actually to verify its feasibility experimentally as a DAS communication network.